Efficient Learning of Sparse Representations with an Energy-Based Model
|
|
- Dorothy Bradford
- 5 years ago
- Views:
Transcription
1 Efficient of Sparse Representations with an Energy-Based Model Marc Aurelio Ranzato, Christopher Poultney, Sumit Chopra, Yann Le Cun Presented by Pascal Lamblin February 14 th, 2007 Efficient of Sparse Representations with an Energy-Based Model
2 1 Pre-processors and feature extractors Coding and decoding 2 Energy Function and Architecture The Sparsifying Logistic 3 4 Feature extraction Initialization of a Convolutional Neural Net Hierarchical Extension: Topographic Maps Si vous vous attendez à lire des bêtises ici, tant pis pour vous
3 Pre-processors and feature extractors Coding and decoding Unsupervised of Representations Methods like PCA, ICA, Wavelet decompositions... Usually, dimensionality is reduced Not necessary: sparse overcomplete representations Improved separability of classes Better interpretation (sum of basic components) Biological parallel (early visual areas) En effet, je resterai d un sérieux exemplaire
4 Usual Architecture Pre-processors and feature extractors Coding and decoding output code input decoder encoder Usually, an encoder and a decoder (possibly sharing parameters) Architecture for auto-encoders, restricted Boltzmann machines, PCA,... Sometimes, the encoder or decoder is absent (e.g., replaced by a sampling or minimization procedure) Here we present a model with an encoder and a decoder Je ne voudrais pas prendre le risque de déconcentrer l auditoire
5 Procedure Pre-processors and feature extractors Coding and decoding Usually (PCA, auto-encoders,... ), we minimize a reconstruction error criterion Here, we also want sparsity in the code: another constraint Use of a Sparsifying Logistic module, between code and decoder Hard to learn through backprop only: optimize a global energy function, which depends also on the codes Iterative coordinate descent optimization (like EM) Mais rendus là, je pense que certains sont déjà perdus
6 Notation and Components Energy Function and Architecture The Sparsifying Logistic The input: an image patch, X, as a vector The encoder: set of linear filters, rows of W C The code: a vector Z The Sparsifying Logistic: transforms Z into Z The sparse code vector: a vector Z with components in [0, 1] The decoder: reverse linear filters, columns of W D Alors rien de mal à leur poser une petite devinette
7 Energy of the System Energy Function and Architecture The Sparsifying Logistic We want to minimize the global energy of the system, function of the model s parameters W C and W D, the free parameter Z, and the input X. E(X, Z, W C, W D ) = E C (X, Z, W C ) + E D (X, Z, W D ) Code prediction energy: E C (X, Z, W C ) = 1 2 Z W C X 2 Reconstruction energy: E C (X, Z, W D ) = 1 X WD Z 2 2 We have no hard equality constraint between Z and W C X, nor on X and W D Z. Z W C X W D Z X Attention, accrochez-vous : qu est-ce qui fait Toin! Toin!?
8 Energy of the System Energy Function and Architecture The Sparsifying Logistic We want to minimize the global energy of the system, function of the model s parameters W C and W D, the free parameter Z, and the input X. E(X, Z, W C, W D ) = E C (X, Z, W C ) + E D (X, Z, W D ) Code prediction energy: E C (X, Z, W C ) = 1 2 Z W C X 2 Reconstruction energy: E C (X, Z, W D ) = 1 X WD Z 2 2 We have no hard equality constraint between Z and W C X, nor on X and W D Z. Z W C X W D Z X Attention, accrochez-vous : qu est-ce qui fait Toin! Toin!?
9 Cool Figure Energy Function and Architecture The Sparsifying Logistic Architecture of the energy-based model Pendant que vous cherchez, on va à la pub
10 In Theory Energy Function and Architecture The Sparsifying Logistic Let s consider the k-th training sample z i (k) = ηeβz i (k) ζ i (k) ζ i (k) = ηe βz i (k) + (1 η)ζ i (k 1) Like a weighted softmax applied through time High values of β makes the values more binary High values of η increases the firing rate The Sparsifying Logistic enforces sparsity through the examples for each individual component. There is no constraint of sparsity between the units of a code. Ragoutoutou! Le ragoût de mon toutou, hmm, j en suis fou!
11 In Practice Energy Function and Architecture The Sparsifying Logistic z i (k) = ηeβz i (k) ζ i (k) z i (k) = (1 η)ζ i(k 1) ηe βz i (k) [ ] 1 z i (k) = 1 + (1 η) η ζ i (k 1)e βz i (k) We learn ζ i across the training set and fix it Logistic function, with fixed gain and learnt bias This version of the Sparsifying Logistic module is deterministic, and does not depend on the ordering of the samples. Continuons dans la détente
12 Procedure We want to minimize: E ( W C, W D, Z 1,..., Z P) = by the procedure: {W C, W D } = argmin {W C,W D } ( P ( ( EC X i, Z i ) (, W C + ED X i, Z i )), W D i=1 ( min E W C, W D, Z 1,..., Z P)) Z 1,...,Z P 1 Find the optimal Z i, given W C and W D 2 Update the weights W C and W D, given Z i found at step 1, in order to minimize the energy 3 Iterate until convergence C est deux vaches qui broutent dans un pré
13 Online Version We consider only one sample X at a time. The cost to minimize is C = E C (X, Z, W C ) + E D (X, Z, W D ) 1 Initialize Z by Z init = W C X 2 Minimize C wrt Z, by gradient descent initialized at Z init 3 Compute the gradient of C wrt W C and W D, and perform one gradient step We iterate over all samples, until convergence. L une dit à l autre : Ça t inquiète pas, ces histoires de vaches folles?
14 So, What Happens? Only a few steps of gradient descent are necessary to minimize Z At the end of the process, even Z init = W C X is accurate enough So E C (X, Z, W C ) = 1 2 Z W C X 2 is minimized The reconstruction errors from Z init are also low So E D (X, Z, W D ) = 1 2 X WD Z 2 is also minimized The minimization procedure manages to minimize both energy terms Imposing the hard constraint W C X = Z does not work, because of the saturation of the sparsifying module An L 1 penalty term is added to W C, and an L 2 penalty term to W D Et l autre répond : Pas du tout, tu vois bien que je suis un lapin!
15 Natural Image Patches Feature extraction Initialization of a Convolutional Neural Net Hierarchical Extension: Topographic Maps patches from the Berkeley segmentation data set Codes of length minutes on a 2 GHz processor for 200 filters on 100, patches Filters learnt by the decoder Spatially localized filters, similar to Gabor wavelets, like receptive fields of V1 neurons W C and W D are really close after the optimization Là, vous pouvez faire semblant de vous intéresser à l exposé : il y a des images
16 On MNIST Digit Recognition Data Set Feature extraction Initialization of a Convolutional Neural Net Hierarchical Extension: Topographic Maps Input is the whole image (not a patch) Codes of length 196 = Some encoder filters, and an example of digit reconstruction Stroke detectors are learnt Reconstruction: sum of a few parts Encore des images, ça aide à patienter jusqu à la fin
17 On MNIST Feature extraction Initialization of a Convolutional Neural Net Hierarchical Extension: Topographic Maps Train filters on 5 5 image patches Codes of length 50 Initialize a network with 50 features on layer 1 and 2, 50 on layer 3 and 4, 200 on layer 5, and 10 output units. Misclassification Random Pre-training No distortions 0.70% 0.60% Distortions 0.49% 0.39% Bon, maintenant le suspense a assez duré
18 Natural Image Patches Feature extraction Initialization of a Convolutional Neural Net Hierarchical Extension: Topographic Maps patches from the Berkeley segmentation data set Codes of length 400 Close filters learn similar weights I NPUT X E d E ucl. Dist. W c W d C ODE L E V E L K = C ONV OL. K Spar s. L ogistic C ODE L E V E L 2 E ucl. Dist. C ODE Z E c La réponse est donc...
19 Energy-based model for unsupervised learning of sparse overcomplete representations Fast and accurate processing after learning Sparsification of each unit across the dataset seems easier than sparsification of each example across the code units Can be extended to non-linear encoder and decoder Sparse code can be used as input for another feature extractor Un tanard! > /
20 Questions? Merci de votre attention
21 Questions? Hopefully not... Merci de votre attention
C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun
Efficient Learning of Sparse Overcomplete Representations with an Energy-Based Model Marc'Aurelio Ranzato C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun CIAR Summer School Toronto 2006 Why Extracting
More informationA Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images
A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract
More informationA Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images
A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract
More informationDeep Learning for Generic Object Recognition
Deep Learning for Generic Object Recognition, Computational and Biological Learning Lab The Courant Institute of Mathematical Sciences New York University Collaborators: Marc'Aurelio Ranzato, Fu Jie Huang,
More informationLearning Feature Hierarchies for Object Recognition
Learning Feature Hierarchies for Object Recognition Koray Kavukcuoglu Computer Science Department Courant Institute of Mathematical Sciences New York University Marc Aurelio Ranzato, Kevin Jarrett, Pierre
More informationIntroduction to Deep Learning
ENEE698A : Machine Learning Seminar Introduction to Deep Learning Raviteja Vemulapalli Image credit: [LeCun 1998] Resources Unsupervised feature learning and deep learning (UFLDL) tutorial (http://ufldl.stanford.edu/wiki/index.php/ufldl_tutorial)
More informationAbout Transferring License Rights for. PL7 V4.5 and Unity Pro V2.3 SP1 Software
Page 1 of 38 Click here to access the English Cliquez ici pour accéder au Français Klicken Sie hier, um zum Deutschen zu gelangen Premete qui per accedere all' Italiano Pulse acquì para acceder al Español
More informationLearning Convolutional Feature Hierarchies for Visual Recognition
Learning Convolutional Feature Hierarchies for Visual Recognition Koray Kavukcuoglu, Pierre Sermanet, Y-Lan Boureau, Karol Gregor, Michael Mathieu, Yann LeCun Computer Science Department Courant Institute
More informationDeep Learning. Volker Tresp Summer 2014
Deep Learning Volker Tresp Summer 2014 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there
More informationLearning-based Methods in Vision
Learning-based Methods in Vision 16-824 Sparsity and Deep Learning Motivation Multitude of hand-designed features currently in use in vision - SIFT, HoG, LBP, MSER, etc. Even the best approaches, just
More informationCS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016
CS 2750: Machine Learning Neural Networks Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 Plan for today Neural network definition and examples Training neural networks (backprop) Convolutional
More informationEfficient Algorithms may not be those we think
Efficient Algorithms may not be those we think Yann LeCun, Computational and Biological Learning Lab The Courant Institute of Mathematical Sciences New York University http://yann.lecun.com http://www.cs.nyu.edu/~yann
More informationDeep Learning Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD.
Deep Learning 861.061 Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD asan.agibetov@meduniwien.ac.at Medical University of Vienna Center for Medical Statistics,
More informationDeep (1) Matthieu Cord LIP6 / UPMC Paris 6
Deep (1) Matthieu Cord LIP6 / UPMC Paris 6 Syllabus 1. Whole traditional (old) visual recognition pipeline 2. Introduction to Neural Nets 3. Deep Nets for image classification To do : Voir la leçon inaugurale
More informationDeep Learning. Deep Learning. Practical Application Automatically Adding Sounds To Silent Movies
http://blog.csdn.net/zouxy09/article/details/8775360 Automatic Colorization of Black and White Images Automatically Adding Sounds To Silent Movies Traditionally this was done by hand with human effort
More informationSparse Feature Learning for Deep Belief Networks
Sparse Feature Learning for Deep Belief Networks Marc Aurelio Ranato 1 Y-Lan Boureau 2,1 Yann LeCun 1 1 Courant Institute of Mathematical Sciences, New York University 2 INRIA Rocquencourt {ranato,ylan,yann@courant.nyu.edu}
More informationDepth Image Dimension Reduction Using Deep Belief Networks
Depth Image Dimension Reduction Using Deep Belief Networks Isma Hadji* and Akshay Jain** Department of Electrical and Computer Engineering University of Missouri 19 Eng. Building West, Columbia, MO, 65211
More informationNeural Networks: promises of current research
April 2008 www.apstat.com Current research on deep architectures A few labs are currently researching deep neural network training: Geoffrey Hinton s lab at U.Toronto Yann LeCun s lab at NYU Our LISA lab
More informationNeural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017
3/0/207 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/0/207 Perceptron as a neural
More informationAlternatives to Direct Supervision
CreativeAI: Deep Learning for Graphics Alternatives to Direct Supervision Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TUM UCL Timetable Theory and Basics State of
More informationUnsupervised Learning
Deep Learning for Graphics Unsupervised Learning Niloy Mitra Iasonas Kokkinos Paul Guerrero Vladimir Kim Kostas Rematas Tobias Ritschel UCL UCL/Facebook UCL Adobe Research U Washington UCL Timetable Niloy
More informationDeep Learning with Tensorflow AlexNet
Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification
More informationHuman Vision Based Object Recognition Sye-Min Christina Chan
Human Vision Based Object Recognition Sye-Min Christina Chan Abstract Serre, Wolf, and Poggio introduced an object recognition algorithm that simulates image processing in visual cortex and claimed to
More informationAkarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction
Akarsh Pokkunuru EECS Department 03-16-2017 Contractive Auto-Encoders: Explicit Invariance During Feature Extraction 1 AGENDA Introduction to Auto-encoders Types of Auto-encoders Analysis of different
More informationAutoencoders, denoising autoencoders, and learning deep networks
4 th CiFAR Summer School on Learning and Vision in Biology and Engineering Toronto, August 5-9 2008 Autoencoders, denoising autoencoders, and learning deep networks Part II joint work with Hugo Larochelle,
More informationCOMP 551 Applied Machine Learning Lecture 16: Deep Learning
COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all
More informationNeural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders
Neural Networks for Machine Learning Lecture 15a From Principal Components Analysis to Autoencoders Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Principal Components
More informationFor Monday. Read chapter 18, sections Homework:
For Monday Read chapter 18, sections 10-12 The material in section 8 and 9 is interesting, but we won t take time to cover it this semester Homework: Chapter 18, exercise 25 a-b Program 4 Model Neuron
More informationSlides adapted from Marshall Tappen and Bryan Russell. Algorithms in Nature. Non-negative matrix factorization
Slides adapted from Marshall Tappen and Bryan Russell Algorithms in Nature Non-negative matrix factorization Dimensionality Reduction The curse of dimensionality: Too many features makes it difficult to
More informationNatural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu
Natural Language Processing CS 6320 Lecture 6 Neural Language Models Instructor: Sanda Harabagiu In this lecture We shall cover: Deep Neural Models for Natural Language Processing Introduce Feed Forward
More informationUnsupervised Learning of Feature Hierarchies
Unsupervised Learning of Feature Hierarchies by Marc Aurelio Ranzato A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy Department of Computer Science
More informationMachine Learning. MGS Lecture 3: Deep Learning
Dr Michel F. Valstar http://cs.nott.ac.uk/~mfv/ Machine Learning MGS Lecture 3: Deep Learning Dr Michel F. Valstar http://cs.nott.ac.uk/~mfv/ WHAT IS DEEP LEARNING? Shallow network: Only one hidden layer
More informationRebuilding Speech Recognition on Windows
Rebuilding Speech Recognition on Windows Haiyan Wang IDIAP-Com 01-09 JANUARY 2001 Dalle Molle Institute for Perceptual Artificial Intelligence P.O.Box 592 Martigny Valais Switzerland phone +41 27 721 77
More informationNeural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing
Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing feature 3 PC 3 Beate Sick Many slides are taken form Hinton s great lecture on NN: https://www.coursera.org/course/neuralnets
More informationYear: 8. Targeted Home Learning. Subject: English
Targeted Home Learning Subject: English Year: 8 Think about the conventions of short stories that you have been learning about this half term. Write your own short story (no more than 300 words). Success
More informationBilevel Sparse Coding
Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013 Outline 1 2 The learning model The learning algorithm 3 4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional
More informationVisual Perception with Deep Learning
Visual Perception with Deep Learning Yann LeCun The Courant Institute of Mathematical Sciences New York University joint work with: Marc'Aurelio Ranzato, Y Lan Boureau, Koray Kavackuoglu, Fu Jie Huang,
More informationCSC 411 Lecture 18: Matrix Factorizations
CSC 411 Lecture 18: Matrix Factorizations Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 18-Matrix Factorizations 1 / 27 Overview Recall PCA: project data
More informationLecture 19: Generative Adversarial Networks
Lecture 19: Generative Adversarial Networks Roger Grosse 1 Introduction Generative modeling is a type of machine learning where the aim is to model the distribution that a given set of data (e.g. images,
More informationOracle Dual Port QDR InfiniBand Adapter M3. Product Notes
Oracle Dual Port QDR InfiniBand Adapter M3 Product Notes Part No.: E40986-01 September 2013 Copyright 2013 Oracle and/or its affiliates. All rights reserved. This software and related documentation are
More informationOracle ZFS Storage Appliance Cabling Guide. For ZS3-x, 7x20 Controllers, and DE2-24, Sun Disk Shelves
Oracle ZFS Storage Appliance Cabling Guide For ZS3-x, 7x20 Controllers, and DE2-24, Sun Disk Shelves Part No: E53670-01 June 2014 Copyright 2009, 2014, Oracle and/or its affiliates. All rights reserved.
More informationDoes the Brain do Inverse Graphics?
Does the Brain do Inverse Graphics? Geoffrey Hinton, Alex Krizhevsky, Navdeep Jaitly, Tijmen Tieleman & Yichuan Tang Department of Computer Science University of Toronto How to learn many layers of features
More informationMachine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart
Machine Learning The Breadth of ML Neural Networks & Deep Learning Marc Toussaint University of Stuttgart Duy Nguyen-Tuong Bosch Center for Artificial Intelligence Summer 2017 Neural Networks Consider
More informationCPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016
CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2016 A2/Midterm: Admin Grades/solutions will be posted after class. Assignment 4: Posted, due November 14. Extra office hours:
More informationMachine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,
Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image
More informationMultiview Feature Learning
Multiview Feature Learning Roland Memisevic Frankfurt, Montreal Tutorial at IPAM 2012 Roland Memisevic (Frankfurt, Montreal) Multiview Feature Learning Tutorial at IPAM 2012 1 / 163 Outline 1 Introduction
More informationUnion of Learned Sparsifying Transforms Based Low-Dose 3D CT Image Reconstruction
Union of Learned Sparsifying Transforms Based Low-Dose 3D CT Image Reconstruction Xuehang Zheng 1, Saiprasad Ravishankar 2, Yong Long 1, Jeff Fessler 2 1 University of Michigan - Shanghai Jiao Tong University
More informationAnalyse statique de programmes avioniques
June 28th 2013. Forum Méthodes Formelles Cycle de conférences: Analyse Statique : «Retour d expériences industrielles» Analyse statique de programmes avioniques Presenté par Jean Souyris (Airbus Opérations
More informationTable of Contents. What Really is a Hidden Unit? Visualizing Feed-Forward NNs. Visualizing Convolutional NNs. Visualizing Recurrent NNs
Table of Contents What Really is a Hidden Unit? Visualizing Feed-Forward NNs Visualizing Convolutional NNs Visualizing Recurrent NNs Visualizing Attention Visualizing High Dimensional Data What do visualizations
More informationImproving the way neural networks learn Srikumar Ramalingam School of Computing University of Utah
Improving the way neural networks learn Srikumar Ramalingam School of Computing University of Utah Reference Most of the slides are taken from the third chapter of the online book by Michael Nielson: neuralnetworksanddeeplearning.com
More informationPréparation au concours ACM TP 2
Préparation au concours ACM TP 2 Christoph Dürr Jill-Jênn Vie September 25, 2014 Quelques conseils Entraînez-vous à identifier les problèmes les plus faciles. Lisez bien les contraintes d affichage : faut-il
More informationUser guide. Bluetooth Keyboard BKB10
User guide Bluetooth Keyboard BKB10 Contents Basics...3 Overview... 3 Charging the keyboard... 4 Turning on the keyboard... 5 Getting started... 6 Setting up the keyboard... 6 Support on the web...6 Legal
More informationCS 179 Lecture 16. Logistic Regression & Parallel SGD
CS 179 Lecture 16 Logistic Regression & Parallel SGD 1 Outline logistic regression (stochastic) gradient descent parallelizing SGD for neural nets (with emphasis on Google s distributed neural net implementation)
More informationDeep Learning for Computer Vision II
IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L
More informationStacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning Mohammad Norouzi, Mani Ranjbar, and Greg Mori School of Computing Science Simon Fraser University Burnaby, BC
More informationDeep Learning Benchmarks Mumtaz Vauhkonen, Quaizar Vohra, Saurabh Madaan Collaboration with Adam Coates, Stanford Unviersity
Deep Learning Benchmarks Mumtaz Vauhkonen, Quaizar Vohra, Saurabh Madaan Collaboration with Adam Coates, Stanford Unviersity Abstract: This project aims at creating a benchmark for Deep Learning (DL) algorithms
More informationEnergy Based Models, Restricted Boltzmann Machines and Deep Networks. Jesse Eickholt
Energy Based Models, Restricted Boltzmann Machines and Deep Networks Jesse Eickholt ???? Who s heard of Energy Based Models (EBMs) Restricted Boltzmann Machines (RBMs) Deep Belief Networks Auto-encoders
More informationExercise: Training Simple MLP by Backpropagation. Using Netlab.
Exercise: Training Simple MLP by Backpropagation. Using Netlab. Petr Pošík December, 27 File list This document is an explanation text to the following script: demomlpklin.m script implementing the beckpropagation
More informationThe exam is closed book, closed notes except your one-page (two-sided) cheat sheet.
CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or
More informationSimple Method for High-Performance Digit Recognition Based on Sparse Coding
1 Simple Method for High-Performance Digit Recognition Based on Sparse Coding Kai Labusch Institute for Neuro- and Bioinformatics University of Lübeck D-23538 Lübeck labusch@inb.uni-luebeck.de Erhardt
More informationAlphabet at School Part 4
Bonjour, je m'appelle Jojo. _ Hello, my name is Jojo. Voici Lulu. Bonjour Lulu. _ There is Lulu. Hello Lulu. Bonjour Jojo _ Hello Jojo. Il est l'heure d'aller a l'école _ It is time to go to school. N'oubliez
More informationTutorial 3: Shortest path Artificial Intelligence
Tutorial 3: Shortest path Artificial Intelligence G.Guérard Les étudiants doivent faire des groupes de 3-4 afin de faire un brainstorming pour chaque exercice. Il n est pas demandé aux étudiants d avoir
More informationEfficient Visual Coding: From Retina To V2
Efficient Visual Coding: From Retina To V Honghao Shan Garrison Cottrell Computer Science and Engineering UCSD La Jolla, CA 9093-0404 shanhonghao@gmail.com, gary@ucsd.edu Abstract The human visual system
More informationKnowledge Engineering Models and Tools for the Digital Scholarly Publishing of Manuscripts
Knowledge Engineering Models and Tools for the Digital Scholarly Publishing of Manuscripts Semantic Web for the Digital Humanities Sahar Aljalbout, Giuseppe Cosenza, Luka Nerima, Gilles Falquet 1 Cultural
More informationNeural Networks and Deep Learning
Neural Networks and Deep Learning Example Learning Problem Example Learning Problem Celebrity Faces in the Wild Machine Learning Pipeline Raw data Feature extract. Feature computation Inference: prediction,
More informationModeling Visual Cortex V4 in Naturalistic Conditions with Invari. Representations
Modeling Visual Cortex V4 in Naturalistic Conditions with Invariant and Sparse Image Representations Bin Yu Departments of Statistics and EECS University of California at Berkeley Rutgers University, May
More informationCS6220: DATA MINING TECHNIQUES
CS6220: DATA MINING TECHNIQUES Image Data: Classification via Neural Networks Instructor: Yizhou Sun yzsun@ccs.neu.edu November 19, 2015 Methods to Learn Classification Clustering Frequent Pattern Mining
More informationarxiv: v2 [cs.lg] 22 Mar 2014
Alireza Makhzani makhzani@psi.utoronto.ca Brendan Frey frey@psi.utoronto.ca University of Toronto, 10 King s College Rd. Toronto, Ontario M5S 3G4, Canada arxiv:1312.5663v2 [cs.lg] 22 Mar 2014 Abstract
More informationCSE 559A: Computer Vision
CSE 559A: Computer Vision Fall 2018: T-R: 11:30-1pm @ Lopata 101 Instructor: Ayan Chakrabarti (ayan@wustl.edu). Course Staff: Zhihao Xia, Charlie Wu, Han Liu http://www.cse.wustl.edu/~ayan/courses/cse559a/
More informationAdvanced Introduction to Machine Learning, CMU-10715
Advanced Introduction to Machine Learning, CMU-10715 Deep Learning Barnabás Póczos, Sept 17 Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio
More informationWhy Normalizing v? Why did we normalize v on the right side? Because we want the length of the left side to be the eigenvalue
Why Normalizing v? Why did we normalize v on the right side? Because we want the length of the left side to be the eigenvalue 1 CCI PCA Algorithm (1) 2 CCI PCA Algorithm (2) 3 PCA from the FERET Face Image
More informationDeep Learning Cook Book
Deep Learning Cook Book Robert Haschke (CITEC) Overview Input Representation Output Layer + Cost Function Hidden Layer Units Initialization Regularization Input representation Choose an input representation
More informationDivya Ramesh December 8, 2014
EE 660 Machine Learning from Signals: Foundations and Methods Project Title: Analysis of Unsupervised Feature Learning Methods for Image Classification Divya Ramesh (dramesh@usc.edu) 5924-4440-58 December
More informationA New Algorithm for Training Sparse Autoencoders
A New Algorithm for Training Sparse Autoencoders Ali Shahin Shamsabadi, Massoud Babaie-Zadeh, Seyyede Zohreh Seyyedsalehi, Hamid R. Rabiee, Christian Jutten Sharif University of Technology, University
More informationReconstruction, Occlusion, Immersion
Reconstruction, Occlusion, Immersion Sébastien Roy Département d Informatique et de recherche opérationnelle Université de Montréal October 28 2005 University of Maryland Overview Two recent algorithms
More informationDeep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group
Deep Learning Vladimir Golkov Technical University of Munich Computer Vision Group 1D Input, 1D Output target input 2 2D Input, 1D Output: Data Distribution Complexity Imagine many dimensions (data occupies
More informationECE 6504: Deep Learning for Perception
ECE 6504: Deep Learning for Perception Topics: (Finish) Backprop Convolutional Neural Nets Dhruv Batra Virginia Tech Administrativia Presentation Assignments https://docs.google.com/spreadsheets/d/ 1m76E4mC0wfRjc4HRBWFdAlXKPIzlEwfw1-u7rBw9TJ8/
More informationLearning Algorithms for Medical Image Analysis. Matteo Santoro slipguru
Learning Algorithms for Medical Image Analysis Matteo Santoro slipguru santoro@disi.unige.it June 8, 2010 Outline 1. learning-based strategies for quantitative image analysis 2. automatic annotation of
More informationTutorial 4: Flow Artificial Intelligence
Tutorial 4: Flow Artificial Intelligence G.Guérard Les étudiants doivent faire des groupes de 3-4 afin de faire un brainstorming pour chaque exercice. Il n est pas demandé aux étudiants d avoir une connaissance
More informationNovel Lossy Compression Algorithms with Stacked Autoencoders
Novel Lossy Compression Algorithms with Stacked Autoencoders Anand Atreya and Daniel O Shea {aatreya, djoshea}@stanford.edu 11 December 2009 1. Introduction 1.1. Lossy compression Lossy compression is
More informationLecture 19: November 5
0-725/36-725: Convex Optimization Fall 205 Lecturer: Ryan Tibshirani Lecture 9: November 5 Scribes: Hyun Ah Song Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer: These notes have not
More informationSelf-Organizing Sparse Codes
Self-Organizing Sparse Codes Yangqing Jia Sergey Karayev 2010-12-16 Abstract Sparse coding as applied to natural image patches learns Gabor-like components that resemble those found in the lower areas
More informationDeep Learning. Deep Learning provided breakthrough results in speech recognition and image classification. Why?
Data Mining Deep Learning Deep Learning provided breakthrough results in speech recognition and image classification. Why? Because Speech recognition and image classification are two basic examples of
More informationCPSC 340: Machine Learning and Data Mining. Deep Learning Fall 2018
CPSC 340: Machine Learning and Data Mining Deep Learning Fall 2018 Last Time: Multi-Dimensional Scaling Multi-dimensional scaling (MDS): Non-parametric visualization: directly optimize the z i locations.
More informationCMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro
CMU 15-781 Lecture 18: Deep learning and Vision: Convolutional neural networks Teacher: Gianni A. Di Caro DEEP, SHALLOW, CONNECTED, SPARSE? Fully connected multi-layer feed-forward perceptrons: More powerful
More informationConditional Random Fields as Recurrent Neural Networks
BIL722 - Deep Learning for Computer Vision Conditional Random Fields as Recurrent Neural Networks S. Zheng, S. Jayasumana, B. Romera-Paredes V. Vineet, Z. Su, D. Du, C. Huang, P.H.S. Torr Introduction
More informationDeep Convolutional Neural Networks. Nov. 20th, 2015 Bruce Draper
Deep Convolutional Neural Networks Nov. 20th, 2015 Bruce Draper Background: Fully-connected single layer neural networks Feed-forward classification Trained through back-propagation Example Computer Vision
More informationWhat is the Best Multi-Stage Architecture for Object Recognition?
What is the Best Multi-Stage Architecture for Object Recognition? Kevin Jarrett, Koray Kavukcuoglu, Marc Aurelio Ranzato and Yann LeCun The Courant Institute of Mathematical Sciences New York University,
More informationSparse arrays of signatures for online character recognition
Sparse arrays of signatures for online character recognition arxiv:1308.0371v2 [cs.cv] 1 Dec 2013 Benjamin Graham Dept of Statistics, University of Warwick, CV4 7AL, UK b.graham@warwick.ac.uk December
More informationSunVTS Quick Reference Card
SunVTS Quick Reference Card Sun Microsystems, Inc. 901 San Antonio Road Palo Alto, CA 94303-4900 U.S.A. 650-960-1300 Part No. 806-6519-10 January 2001, Revision A Send comments about this document to:
More informationNatural Language Processing
Natural Language Processing Classification III Dan Klein UC Berkeley 1 Classification 2 Linear Models: Perceptron The perceptron algorithm Iteratively processes the training set, reacting to training errors
More informationMachine Learning for Physicists Lecture 6. Summer 2017 University of Erlangen-Nuremberg Florian Marquardt
Machine Learning for Physicists Lecture 6 Summer 2017 University of Erlangen-Nuremberg Florian Marquardt Channels MxM image MxM image K K 3 channels conv 6 channels in any output channel, each pixel receives
More informationContractive Auto-Encoders: Explicit Invariance During Feature Extraction
: Explicit Invariance During Feature Extraction Salah Rifai (1) Pascal Vincent (1) Xavier Muller (1) Xavier Glorot (1) Yoshua Bengio (1) (1) Dept. IRO, Université de Montréal. Montréal (QC), H3C 3J7, Canada
More informationCanada s Energy Future:
Page 1 of 9 1DWLRQDO (QHUJ\ %RDUG 2IILFH QDWLRQDO GH OҋpQHUJLH Canada s Energy Future: ENERGY SUPPLY AND DEMAND PROJECTIONS TO 2035 Appendices AN ENERGY MARKET ASSESSMENT NOVEMBER 2011 Page 2 of 9 Canada
More informationFacial Expression Classification with Random Filters Feature Extraction
Facial Expression Classification with Random Filters Feature Extraction Mengye Ren Facial Monkey mren@cs.toronto.edu Zhi Hao Luo It s Me lzh@cs.toronto.edu I. ABSTRACT In our work, we attempted to tackle
More informationMardi 3 avril Epreuve écrite sur un document en anglais
C O L L E CONCOURS INTERNE ET EXTERNE DE TECHNICIEN DE CLASSE NORMALE DES SYSTEMES D INFORMATION ET DE COMMUNICATION Ne pas cacher le cadre d identité. Cette opération sera réalisée par l administration
More informationROTATION INVARIANT SPARSE CODING AND PCA
ROTATION INVARIANT SPARSE CODING AND PCA NATHAN PFLUEGER, RYAN TIMMONS Abstract. We attempt to encode an image in a fashion that is only weakly dependent on rotation of objects within the image, as an
More informationArtificial Intelligence Introduction Handwriting Recognition Kadir Eren Unal ( ), Jakob Heyder ( )
Structure: 1. Introduction 2. Problem 3. Neural network approach a. Architecture b. Phases of CNN c. Results 4. HTM approach a. Architecture b. Setup c. Results 5. Conclusion 1.) Introduction Artificial
More informationClasses internes, Classes locales, Classes anonymes
Classes internes, Classes locales, Classes anonymes Victor Marsault Aldric Degorre CPOO 2015 Enum (1) 2 Quand les utiliser: disjonctions de cas type au sens courant (eg. type de messages d erreur, type
More informationGraphes: Manipulations de base et parcours
Graphes: Manipulations de base et parcours Michel Habib habib@liafa.univ-paris-diderot.fr http://www.liafa.univ-paris-diderot.fr/~habib Cachan, décembre 2013 Notations Here we deal with finite loopless
More information